Wee Peng Tay
Papers
6
Total Citations
636
H-Index
5
About
Wee Peng Tay is a researcher whose work spans robotics, autonomous systems, and sensor fusion, with particular expertise in localization, mapping, and 3D computer vision. His most influential contribution — a 2012 paper on cloud robotics architecture (484 citations) — laid foundational groundwork for extending the computational and communication capabilities of networked robots through machine-to-machine connectivity and cloud infrastructure, helping to shape how the robotics community thinks about distributed intelligence. Building on this systems-level thinking, Tay has since pursued robust real-world localization solutions, including a UWB/LiDAR fusion framework for cooperative range-only SLAM (96 citations), which enables mobile robots to map unknown environments collaboratively using heterogeneous sensor networks. His more recent research reflects a growing focus on deep learning for 3D perception, including transformer- and diffusion-based point cloud registration (PointDifformer), hyperbolic geometry-informed LiDAR pose regression (HypLiLoc), and multi-modal place recognition combining image and point cloud data. Across these efforts, Tay consistently addresses challenges of robustness, efficiency, and scalability — qualities critical to real-world deployment in autonomous driving and robotics. His body of work demonstrates a coherent trajectory from networked robotic architectures toward intelligent, perception-driven autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Cloud robotics: architecture, challenges and applications484 citations · 2012
- 2UWB/LiDAR Fusion For Cooperative Range-Only SLAM96 citations · 2019
- 3
- 4HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion19 citations · 2023
- 5
- 6HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion2 citations · 2023